MEMORY.md Full Snapshot (2026-09-27)
> Full historical snapshots are archived in the external memory hub (latest: 178635208). Only the core skeleton is kept locally.
Core Preferences
- Papers → zhichai.net | Writing → Feynman style | Before publishing: search first to confirm
- Language: concise Chinese, ample emoji, clear Markdown sections
- Main posts use the Xiaokai token, follow-up comments use the Qianxun token
- Master index: https://zhichai.net/t/178635209 (cron-synced 09-26 03:17 ✓; create a new summary topic when content changes)
- Full snapshot: https://zhichai.net/t/178635208 (cron auto-published 09-26 02:17 ✓)
- Old archive: https://zhichai.net/t/178633778
- [ ] P0 Daily paper recommendation - PapersCool (07:16) repeatedly timing out — suggest disabling; the 08:40 pipeline already covers it
- [ ] P2 Choose one of the two paper pipelines (07:16 times out vs. 08:40 OK; risk of duplicate publishing)
- [ ] P2 Fix the zhichai tag system
- [ ] P2 Paper title truncation (e.g., topic 178635100 ends with "G...")
- [ ] P2 Paper author list truncation (>10 authors → et al.)
- [ ] P2 Unify memory index (three coexisting copies → reply-to-master-index mode) + update SKILL.md index ID (177619566 → 178633778)
- [ ] P2 Fix field-name matching in ai_publisher.py
- [ ] P2 Cross-pipeline deduplication for papers (search arXiv ID before publishing)
- [ ] P2 Fix paper topic-category classification
- [ ] P2 Standardize paper title formatting
- [ ] P2 Reduce frequency of / pause easy-learn-ai monitoring (inactive for 74+ days; awaiting a decision)
- VIX inflection warning (09-25): after bottoming at 14.21 on 9/22, VIX rebounded +10.3% over two days, closing at 15.67. Holding above 15.5 → compression ending; breaking below 14.5 → false rebound.
Recent Output Index
To-Do Queue
Live Signal
*Sync time: 2026-09-27 02:17 (cron memory-sync-mempalace)*